© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 7748
    Prev
    Next
    INDEX
    Explanations

    corporate names and associated financial or legal terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.50
     Conjug
    -0.47
     protoimpl
    -0.44
    Datuak
    -0.44
     Confession
    -0.42
    Conjug
    -0.42
     Conscience
    -0.42
    Claus
    -0.41
     Chwiliwch
    -0.40
     Administrativna
    -0.40
    POSITIVE LOGITS
     cor
    2.25
     kor
    2.08
     Cor
    2.05
    Cor
    2.03
    cor
    2.00
     COR
    1.98
    COR
    1.93
     Kor
    1.88
    Kor
    1.77
    kor
    1.70
    Activations Density 1.412%

    No Known Activations